© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59151
    Prev
    Next
    INDEX
    Explanations

    top of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¼¥
    -0.10
    继
    -0.09
    æĽ´å¤ļçļĦæĺ¯
    -0.09
    èŀį
    -0.09
     Join
    -0.09
    丰åİļ
    -0.09
    èĦijåŃIJ
    -0.08
    ç¼µ
    -0.08
    metics
    -0.08
    Disposition
    -0.08
    POSITIVE LOGITS
    éļ¨æĻĤ
    0.09
    èĺ¸
    0.09
    åĪĨæķ£
    0.08
    åķľ
    0.08
    éħĭ
    0.08
    éļıæŶ
    0.08
    åį³åı¯
    0.08
    éħįå¥Ĺ
    0.08
    .blob
    0.08
    .fm
    0.08
    Activations Density 0.009%

    No Known Activations